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

    Neuronpedia

    INDEX
    Explanations

    content generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beans
    -0.07
     Presence
    -0.06
     ben
    -0.06
     yanı
    -0.06
    float
    -0.06
     vstup
    -0.06
    Lemma
    -0.06
    ested
    -0.06
    pieces
    -0.06
    BLACK
    -0.06
    POSITIVE LOGITS
     Intermediate
    0.07
    枪
    0.06
    ’↵↵
    0.06
     Phi
    0.06
    晚
    0.06
     Amateur
    0.06
     Latin
    0.06
    FT
    0.06
    SENT
    0.06
    WF
    0.06
    Act Density 0.030%

    No Known Activations