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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pull
    -0.07
     baptism
    -0.07
     headed
    -0.07
     attach
    -0.07
    _chr
    -0.07
     denote
    -0.07
     missile
    -0.06
     herk
    -0.06
     XS
    -0.06
    errmsg
    -0.06
    POSITIVE LOGITS
    TEMPL
    0.07
     afterward
    0.06
     наб
    0.06
    .po
    0.06
     nákup
    0.06
    (tableName
    0.06
    .BO
    0.06
    dato
    0.06
    icion
    0.06
    ाम
    0.06
    Act Density 0.049%

    No Known Activations