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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ewidth
    -0.07
    	matrix
    -0.07
     инфек
    -0.07
     sempre
    -0.06
     lég
    -0.06
    ochastic
    -0.06
    енд
    -0.06
     jamais
    -0.06
     snapshots
    -0.06
    (defun
    -0.06
    POSITIVE LOGITS
    lah
    0.07
     INDIRECT
    0.07
    yth
    0.07
     Sylv
    0.06
    による
    0.06
     баг
    0.06
    intValue
    0.06
    —they
    0.06
    걸
    0.06
    izza
    0.06
    Act Density 0.035%

    No Known Activations