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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrasts or situations involving positive and negative outcomes

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

    idiomatic phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.61
     Италијани
    -0.56
    :+:
    -0.52
    IUrlHelper
    -0.45
     jsPsych
    -0.42
     Signalez
    -0.41
    fromnode
    -0.41
    #+#
    -0.41
    $_['
    -0.40
     CommonModule
    -0.40
    POSITIVE LOGITS
    ChildScrollView
    0.56
    雳
    0.51
    iettivo
    0.50
     morango
    0.49
     testimonials
    0.49
     whiteColor
    0.49
    mozilla
    0.48
     muualla
    0.48
     Bere
    0.46
     adorable
    0.46
    Act Density 0.048%

    No Known Activations