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

    Neuronpedia

    INDEX
    Explanations

    continuation of a list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dek
    -0.07
     monde
    -0.07
    τικών
    -0.07
     キャ
    -0.07
    _SEQ
    -0.06
    )?↵
    -0.06
    runner
    -0.06
    헤
    -0.06
     stellt
    -0.06
    _LL
    -0.06
    POSITIVE LOGITS
     etc
    0.07
     stup
    0.06
    \ActiveForm
    0.06
    dating
    0.06
    asaki
    0.05
    cox
    0.05
     porrf
    0.05
     學
    0.05
     أم
    0.05
     永
    0.05
    Act Density 0.017%

    No Known Activations