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

    Neuronpedia

    INDEX
    Explanations

    personal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    रण
    -0.08
     Towers
    -0.07
    <algorithm
    -0.07
    �
    -0.07
    ,next
    -0.07
    Monkey
    -0.07
    ็ค
    -0.06
    DCF
    -0.06
    Chess
    -0.06
    بل
    -0.06
    POSITIVE LOGITS
     styled
    0.07
    .setName
    0.06
     functional
    0.06
    озвращает
    0.06
    .where
    0.06
    STRING
    0.06
    ViewModel
    0.06
    aşı
    0.06
     eax
    0.06
    %%*/
    0.06
    Act Density 0.003%

    No Known Activations