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

    Neuronpedia

    INDEX
    Explanations

    surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     KMeans
    0.38
     testicule
    0.37
     fitur
    0.32
     MetaMask
    0.32
     Hasta
    0.31
    側の
    0.31
     solucionar
    0.31
     touchpad
    0.31
     DBox
    0.31
     Colombeau
    0.31
    POSITIVE LOGITS
    on
    0.42
    ag
    0.41
    ne
    0.41
    is
    0.40
    ian
    0.40
    en
    0.39
    ite
    0.39
     and
    0.38
    ice
    0.38
    re
    0.38
    Act Density 0.014%

    No Known Activations