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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cession
    -0.07
    '^
    -0.07
    积极探索
    -0.07
     caractère
    -0.07
    arching
    -0.07
    즌
    -0.06
    cc
    -0.06
    TK
    -0.06
    )sender
    -0.06
    שיבה
    -0.06
    POSITIVE LOGITS
     drops
    0.07
    .histogram
    0.07
    平稳
    0.07
    大概是
    0.06
    Temporary
    0.06
     Hulk
    0.06
    蝴
    0.06
    ন
    0.06
    𝙾
    0.06
     Truck
    0.06
    Act Density 0.000%

    No Known Activations