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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stunden
    -0.07
    meldung
    -0.07
    �
    -0.07
     stall
    -0.07
     Substitute
    -0.07
    ure
    -0.07
    cession
    -0.06
    ımızın
    -0.06
    oma
    -0.06
    ören
    -0.06
    POSITIVE LOGITS
     dato
    0.06
    .Chart
    0.06
    GRID
    0.06
     ल
    0.06
    _BUF
    0.06
     cmd
    0.06
     annual
    0.06
    _MUL
    0.06
     dentro
    0.06
    .;↵
    0.06
    Act Density 0.003%

    No Known Activations