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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AB
    -0.07
     smtp
    -0.07
    _CONTINUE
    -0.07
     UNUSED
    -0.06
     München
    -0.06
     coded
    -0.06
     Enabled
    -0.06
     mnoha
    -0.06
    	R
    -0.06
    خاب
    -0.06
    POSITIVE LOGITS
     reimbursement
    0.07
     trope
    0.07
     trading
    0.06
    coln
    0.06
    ほど
    0.06
    .Router
    0.06
    rı
    0.06
    _SCALE
    0.06
     SignUp
    0.06
     Nepal
    0.06
    Act Density 0.001%

    No Known Activations