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

    Neuronpedia

    INDEX
    Explanations

    summarize google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Escape
    0.48
    eritud
    0.44
    URI
    0.43
    われた
    0.43
    UInteger
    0.41
    Galer
    0.41
    mba
    0.41
    Mem
    0.41
    verture
    0.41
    Fn
    0.41
    POSITIVE LOGITS
     số
    0.47
     abundante
    0.47
     Hydrogen
    0.46
     hydrogens
    0.46
     lipids
    0.44
     мы
    0.44
     đỡ
    0.43
     số
    0.43
    ucky
    0.43
     algún
    0.43
    Act Density 0.001%

    No Known Activations