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

    Neuronpedia

    INDEX
    Explanations

    Giving Advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erre
    -0.07
     Honestly
    -0.07
     zatím
    -0.07
     Simulation
    -0.07
    uppe
    -0.06
     Bolshevik
    -0.06
     viral
    -0.06
     Wildcats
    -0.06
    jsc
    -0.06
    .Linear
    -0.06
    POSITIVE LOGITS
     principalColumn
    0.06
    }');↵
    0.06
    .↵↵↵↵↵
    0.06
     ViewChild
    0.06
     getTotal
    0.06
     excess
    0.06
    Spirit
    0.06
    SECTION
    0.06
    -master
    0.06
    ][/
    0.06
    Act Density 0.034%

    No Known Activations