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
    	dist
    -0.07
     Ahmad
    -0.07
    	idx
    -0.06
    variably
    -0.06
     automated
    -0.06
     Ryu
    -0.06
     RH
    -0.06
    Guy
    -0.06
     muj
    -0.06
     Μα
    -0.06
    POSITIVE LOGITS
    ptions
    0.07
    ーパ
    0.07
    chest
    0.07
    aving
    0.07
    _ES
    0.07
    abar
    0.07
    .NOT
    0.07
     producing
    0.06
     اهم
    0.06
    Monkey
    0.06
    Act Density 0.015%

    No Known Activations