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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fs
    -0.07
    FS
    -0.07
    елей
    -0.06
     transmit
    -0.06
     recruits
    -0.06
    
    -0.06
     occurs
    -0.06
     decreases
    -0.06
     inject
    -0.06
    نين
    -0.06
    POSITIVE LOGITS
    .Setter
    0.07
     aldı
    0.07
    tweets
    0.06
     Έ
    0.06
     omas
    0.06
     accompl
    0.06
     Você
    0.06
     Redistributions
    0.06
     Ctrl
    0.06
    epoch
    0.06
    Act Density 0.001%

    No Known Activations