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

    Neuronpedia

    INDEX
    Explanations

    numeric dimensions and measurements

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

    dimensions with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.86
    fjspx
    -0.64
    UrlResolution
    -0.63
     deſſen
    -0.57
    ſelben
    -0.57
     snippetHide
    -0.57
     betweenstory
    -0.57
     Walkover
    -0.56
     argint
    -0.56
     unſer
    -0.54
    POSITIVE LOGITS
    ждый
    0.32
     sederhana
    0.31
    horabuena
    0.29
    expandindo
    0.29
    Natural
    0.28
     causa
    0.27
    gen
    0.27
    gan
    0.27
    WithIdentifier
    0.27
    Stopped
    0.27
    Act Density 0.081%

    No Known Activations