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

    Neuronpedia

    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Covers
    -0.07
    rolls
    -0.07
     الدين
    -0.06
    _python
    -0.06
     Beans
    -0.06
    opathic
    -0.06
    ΑΛ
    -0.06
     фил
    -0.06
    .sequence
    -0.06
     мер
    -0.06
    POSITIVE LOGITS
    iyor
    0.07
     Assault
    0.06
    713
    0.06
    IF
    0.06
    	J
    0.06
     tightening
    0.06
     HT
    0.06
     PI
    0.06
    GR
    0.06
    urchased
    0.06
    Act Density 0.000%

    No Known Activations