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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     citrus
    -0.07
     Selected
    -0.06
     Saving
    -0.06
    .substr
    -0.06
    findOne
    -0.06
     στο
    -0.06
    -python
    -0.06
    minimal
    -0.06
     condiciones
    -0.06
    EMALE
    -0.06
    POSITIVE LOGITS
    cmpeq
    0.08
     coeff
    0.06
     rewards
    0.06
     кал
    0.06
     Koch
    0.06
    >Add
    0.06
    	mc
    0.06
     moments
    0.06
    ($__
    0.06
    .uc
    0.06
    Act Density 0.001%

    No Known Activations