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

    Neuronpedia

    INDEX
    Explanations

    shared experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alternatively
    -0.07
     probabilities
    -0.07
    .hstack
    -0.07
     progressed
    -0.06
    ----↵↵
    -0.06
     infancy
    -0.06
    esktop
    -0.06
    ierz
    -0.06
     melodies
    -0.06
     toString
    -0.06
    POSITIVE LOGITS
     BASE
    0.07
     код
    0.07
     bounce
    0.06
    aint
    0.06
    ��作
    0.06
     intuitive
    0.06
     CPC
    0.06
     ease
    0.06
    -binary
    0.06
    _SOC
    0.06
    Act Density 0.021%

    No Known Activations