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

    Neuronpedia

    INDEX
    Explanations

    halting actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dbl
    -0.07
     Cluster
    -0.07
     HA
    -0.07
    Content
    -0.06
    kelig
    -0.06
    uen
    -0.06
    856
    -0.06
     proletariat
    -0.06
     ():
    -0.06
    itory
    -0.06
    POSITIVE LOGITS
    cly
    0.07
     �
    0.06
    .Disabled
    0.06
    customers
    0.06
     manifestations
    0.06
     physiology
    0.06
    _chk
    0.06
    device
    0.05
     terrain
    0.05
    detail
    0.05
    Act Density 0.048%

    No Known Activations