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

    Neuronpedia

    INDEX
    Explanations

    UR robots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     persona
    -0.09
     seção
    -0.08
     অধ
    -0.08
     Persona
    -0.08
     inglês
    -0.07
     majd
    -0.07
     compens
    -0.07
     retained
    -0.07
     Italiano
    -0.07
     retaining
    -0.07
    POSITIVE LOGITS
    すると
    0.07
    џ
    0.07
    ませ
    0.07
    ити
    0.07
    ません
    0.07
    Village
    0.07
     faibles
    0.07
    �
    0.07
     കൊണ്ട
    0.07
    _layers
    0.07
    Act Density 0.000%

    No Known Activations