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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trust
    -0.08
     schm
    -0.08
    (tr
    -0.08
    .tr
    -0.07
    /the
    -0.07
     shrink
    -0.07
     довер
    -0.07
     pervers
    -0.07
    Grey
    -0.07
    /store
    -0.07
    POSITIVE LOGITS
     মার্চ
    0.08
     responding
    0.08
     উঠ
    0.08
     PROC
    0.08
    encoded
    0.07
     Respond
    0.07
     Opc
    0.07
     Charleston
    0.07
     proporcional
    0.07
     호출
    0.07
    Act Density 0.001%

    No Known Activations