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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clippers
    -0.07
     rotates
    -0.07
     Pat
    -0.07
     =&
    -0.06
    �
    -0.06
    mel
    -0.06
     sockets
    -0.06
     Stoke
    -0.06
    _NEG
    -0.06
     animal
    -0.06
    POSITIVE LOGITS
     след
    0.06
    방송
    0.06
     qualified
    0.06
     ★
    0.06
    Executing
    0.06
    .restore
    0.06
    类型
    0.06
     columna
    0.06
     EXEMPLARY
    0.06
     advisable
    0.06
    Act Density 0.023%

    No Known Activations