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

    Neuronpedia

    INDEX
    Explanations

    calculator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rex
    -0.07
    endent
    -0.07
    بصر
    -0.07
     aspects
    -0.07
     STATUS
    -0.07
    .Anchor
    -0.06
    冲
    -0.06
     Cross
    -0.06
    г
    -0.06
     الو
    -0.06
    POSITIVE LOGITS
    Animator
    0.07
     clinicians
    0.07
     أد
    0.07
    ipeline
    0.07
    けば
    0.07
    )||(
    0.07
    “If
    0.07
     dames
    0.07
     annot
    0.07
     Druid
    0.07
    Act Density 0.003%

    No Known Activations