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

    Neuronpedia

    INDEX
    Explanations

    che

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Matrix
    -0.07
     uphill
    -0.06
     Supplements
    -0.06
     �
    -0.06
    ucción
    -0.06
    CloseOperation
    -0.06
     erupted
    -0.06
     implants
    -0.06
    endon
    -0.06
     explodes
    -0.06
    POSITIVE LOGITS
     sensitivity
    0.07
    box
    0.07
    sexy
    0.06
    Define
    0.06
    ฬ
    0.06
     Korea
    0.06
     undesirable
    0.06
     Sexy
    0.06
    ANY
    0.06
    Der
    0.06
    Act Density 0.029%

    No Known Activations