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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .compute
    -0.07
    _tp
    -0.06
    ��
    -0.06
    _scene
    -0.06
    カー
    -0.06
     slashing
    -0.06
     rely
    -0.06
     rail
    -0.06
     responders
    -0.06
    aug
    -0.06
    POSITIVE LOGITS
     التج
    0.07
    inheritDoc
    0.07
     Amer
    0.06
    	ar
    0.06
    Aura
    0.06
     Finger
    0.06
    Emer
    0.06
    冊
    0.06
     verificar
    0.06
     szcz
    0.06
    Act Density 0.000%

    No Known Activations