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

    Neuronpedia

    INDEX
    Explanations

    insert hyperlink or link

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gab
    0.43
    /+
    0.43
     engagement
    0.41
    uland
    0.40
     Usa
    0.38
     alleys
    0.37
     alley
    0.36
     FirebaseAuth
    0.36
     siga
    0.36
     గారి
    0.36
    POSITIVE LOGITS
    ፈላጊ
    0.46
    ัป
    0.45
    Datos
    0.44
     površ
    0.42
    კო
    0.41
     危
    0.41
     variáveis
    0.40
     противоре
    0.40
    瀉
    0.40
    洩
    0.39
    Act Density 0.001%

    No Known Activations