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

    Neuronpedia

    INDEX
    Explanations

    watched

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Backup
    -0.07
     advisory
    -0.07
     haber
    -0.06
    .models
    -0.06
    ा।
    -0.06
     observes
    -0.06
    service
    -0.06
    (next
    -0.06
    ，就
    -0.06
     admiration
    -0.06
    POSITIVE LOGITS
    >NN
    0.07
     Ces
    0.06
    xDF
    0.06
    軟
    0.06
     lettre
    0.06
    .styleable
    0.06
     belle
    0.06
     rocky
    0.06
     triang
    0.06
    ジュ
    0.06
    Act Density 0.020%

    No Known Activations