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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    匮
    -0.08
    ologies
    -0.07
    opoulos
    -0.07
     spouses
    -0.07
     nf
    -0.07
    ourn
    -0.07
    _cp
    -0.07
    璟
    -0.06
    ahkan
    -0.06
    ilians
    -0.06
    POSITIVE LOGITS
    围绕
    0.07
    %D
    0.07
     quelque
    0.07
    猜
    0.07
     brow
    0.07
    CANCEL
    0.07
     %@",
    0.06
    .dropdown
    0.06
    さまざまな
    0.06
    _vote
    0.06
    Act Density 0.051%

    No Known Activations