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

    Neuronpedia

    INDEX
    Explanations

    Your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    υχ
    -0.06
     forwards
    -0.06
     wizards
    -0.06
    ifiable
    -0.06
    olving
    -0.06
     would
    -0.06
    都会
    -0.06
    _REPLACE
    -0.06
     Modular
    -0.06
     HERE
    -0.06
    POSITIVE LOGITS
     kosten
    0.06
    _lifetime
    0.06
     infant
    0.06
    .embed
    0.06
     goalie
    0.06
    tweets
    0.06
     휴
    0.06
     nan
    0.06
     axiom
    0.06
    indsight
    0.06
    Act Density 0.007%

    No Known Activations