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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tinder
    -0.07
    .enums
    -0.06
     cops
    -0.06
    	hit
    -0.06
     अध
    -0.06
    ,address
    -0.06
    दम
    -0.06
     amatør
    -0.06
    drv
    -0.06
     подоб
    -0.06
    POSITIVE LOGITS
    ehen
    0.07
    	error
    0.07
    [pos
    0.06
    Lambda
    0.06
     jLabel
    0.06
    territ
    0.06
     Occup
    0.06
    fea
    0.06
     replen
    0.06
    JK
    0.06
    Act Density 0.001%

    No Known Activations