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
     Stage
    -0.08
    172
    -0.07
     como
    -0.07
    사무
    -0.07
    	perror
    -0.07
     chor
    -0.07
    uke
    -0.07
     stati
    -0.07
    17
    -0.07
     Honor
    -0.07
    POSITIVE LOGITS
     �
    0.08
    raham
    0.07
    гал
    0.07
    .is
    0.06
    …and
    0.06
    
    0.06
    应用
    0.06
    �
    0.06
    .In
    0.06
    ycles
    0.06
    Act Density 0.003%

    No Known Activations