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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raft
    -0.07
    ERG
    -0.06
     obedient
    -0.06
     FRE
    -0.06
    DBG
    -0.06
    156
    -0.06
     prevState
    -0.06
     alliances
    -0.06
    Fade
    -0.06
     Berkeley
    -0.06
    POSITIVE LOGITS
    >Edit
    0.07
    .DataPropertyName
    0.06
     наві
    0.06
    .removeAttribute
    0.06
    描
    0.06
    \e
    0.06
     року
    0.06
    FI
    0.06
    /Login
    0.06
    定义
    0.06
    Act Density 0.022%

    No Known Activations