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

    Neuronpedia

    INDEX
    Explanations

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liverpool
    -0.07
     reveals
    -0.07
    },
    -0.06
     ph
    -0.06
    Ins
    -0.06
     About
    -0.06
    :**
    -0.06
     expo
    -0.06
     somewhat
    -0.06
    Liverpool
    -0.06
    POSITIVE LOGITS
     دسته
    0.07
    _State
    0.07
    覚
    0.07
    ania
    0.07
    jist
    0.06
    础
    0.06
    ackBar
    0.06
    Redis
    0.06
     localize
    0.06
    ışı
    0.06
    Act Density 0.030%

    No Known Activations