Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of numbers and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or unusual formatting

    np_acts-logits-general · gemini-2.0-flash

    this phase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jereo
    -0.61
    GOTREF
    -0.53
     victimes
    -0.52
    ategorias
    -0.51
    isticas
    -0.49
    mentação
    -0.48
    FXML
    -0.47
    łby
    -0.47
     stabilized
    -0.46
     jerawat
    -0.46
    POSITIVE LOGITS
    ⓧ
    0.67
    !*\
    0.61
    Personensuche
    0.58
     MessageBoxIcon
    0.57
     Waray
    0.55
    ProgressHUD
    0.54
    Autoritní
    0.52
    bibfield
    0.52
     smtplib
    0.51
    IUrlHelper
    0.49
    Act Density 0.015%

    No Known Activations