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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्रब
    -0.07
     dare
    -0.06
     odbor
    -0.06
    leich
    -0.06
     sous
    -0.06
    Дата
    -0.06
    apyrus
    -0.06
    occan
    -0.06
     Serge
    -0.06
     dared
    -0.06
    POSITIVE LOGITS
     signs
    0.07
     process
    0.06
    Artifact
    0.06
    ulus
    0.06
    页
    0.06
     knowledge
    0.06
    rq
    0.06
    }()↵
    0.06
     experienced
    0.06
    .textLabel
    0.06
    Act Density 0.000%

    No Known Activations