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

    Neuronpedia

    INDEX
    Explanations

    knife

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preds
    -0.07
     세
    -0.07
     và
    -0.07
    麦
    -0.07
    outline
    -0.06
    Into
    -0.06
     promoted
    -0.06
    ré
    -0.06
     Specifications
    -0.06
     pres
    -0.06
    POSITIVE LOGITS
    ]},↵
    0.06
    itch
    0.06
    )"},↵
    0.06
    "}},↵
    0.06
    _MISS
    0.06
     holistic
    0.06
    .IsSuccess
    0.06
    keeping
    0.06
    ControlEvents
    0.06
    чини
    0.06
    Act Density 0.031%

    No Known Activations