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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /unit
    -0.07
    /sec
    -0.06
    .ast
    -0.06
     вуз
    -0.06
    four
    -0.06
    組
    -0.06
    根
    -0.06
    perial
    -0.06
     Filip
    -0.06
    hape
    -0.06
    POSITIVE LOGITS
    デ
    0.07
     исключ
    0.07
     overseeing
    0.06
     denotes
    0.06
     Comedy
    0.06
     workaround
    0.06
     메
    0.06
     markedly
    0.06
    _TOPIC
    0.06
     mensen
    0.06
    Act Density 0.005%

    No Known Activations