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

    Neuronpedia

    INDEX
    Explanations

    dise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taxonomy
    -0.06
    ingular
    -0.06
    opal
    -0.06
     иногда
    -0.06
    oley
    -0.06
    $rows
    -0.06
    児
    -0.06
     Car
    -0.05
     pj
    -0.05
     poles
    -0.05
    POSITIVE LOGITS
    -spe
    0.08
    ASIC
    0.08
     فهم
    0.07
     стил
    0.07
    -sheet
    0.07
     prostituerte
    0.07
     المك
    0.07
    設計
    0.07
    je
    0.07
    \E
    0.07
    Act Density 0.001%

    No Known Activations