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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ஹ
    -0.07
    Overrides
    -0.07
    /ch
    -0.06
     vet
    -0.06
    �
    -0.06
     bother
    -0.06
     ❤
    -0.06
    טופ
    -0.06
    ites
    -0.06
    䲠
    -0.06
    POSITIVE LOGITS
    巡逻
    0.08
     Original
    0.08
    宁波
    0.07
     Spiel
    0.07
     Rossi
    0.07
     compressed
    0.07
     convenience
    0.07
    ichage
    0.07
     LS
    0.07
     hobby
    0.07
    Act Density 0.018%

    No Known Activations