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

    Neuronpedia

    INDEX
    Explanations

    Code and regex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fit
    -0.07
    _mutex
    -0.06
     zoals
    -0.06
    justify
    -0.06
    -begin
    -0.06
     hơi
    -0.06
     більше
    -0.06
    Signals
    -0.06
     allocating
    -0.06
     markedly
    -0.06
    POSITIVE LOGITS
     Wrestling
    0.07
    osloven
    0.07
     температуры
    0.06
    “Oh
    0.06
    __);↵
    0.06
     solidity
    0.06
    lyn
    0.06
    .m
    0.06
    duino
    0.06
     anarchist
    0.06
    Act Density 0.083%

    No Known Activations