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

    Neuronpedia

    INDEX
    Explanations

    reports and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >f
    -0.06
     lw
    -0.06
    _PERSON
    -0.06
    Vars
    -0.06
     layoffs
    -0.06
    ece
    -0.06
    ящих
    -0.06
    endency
    -0.06
    >m
    -0.06
    prof
    -0.06
    POSITIVE LOGITS
    (ident
    0.07
     عشر
    0.06
     자신의
    0.06
    igail
    0.06
    Expanded
    0.06
    cstring
    0.06
     σχ
    0.06
     Nullable
    0.06
    ipher
    0.06
     αγ
    0.06
    Act Density 0.042%

    No Known Activations