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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    35
    -0.07
    应当
    -0.06
    子供
    -0.06
    _below
    -0.06
     comforting
    -0.06
    butt
    -0.06
    .JsonIgnore
    -0.06
    拔
    -0.06
     Answers
    -0.06
     acknowledging
    -0.06
    POSITIVE LOGITS
    wizard
    0.07
    ARGET
    0.06
     saldır
    0.06
    .apple
    0.06
    莉
    0.06
    marine
    0.06
    registers
    0.06
    (getString
    0.06
    NECT
    0.06
    シー
    0.06
    Act Density 0.057%

    No Known Activations