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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authenticate
    -0.07
     times
    -0.06
     vener
    -0.06
     pam
    -0.06
    ��
    -0.06
    ########################################
    -0.06
    ibration
    -0.06
    пис
    -0.06
     refuse
    -0.06
     Вики
    -0.06
    POSITIVE LOGITS
     {'
    0.07
     charg
    0.07
    (toolbar
    0.07
     reversal
    0.07
    =array
    0.06
    lots
    0.06
    (UInt
    0.06
     tri
    0.06
     Clin
    0.06
     practices
    0.06
    Act Density 0.083%

    No Known Activations