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

    Neuronpedia

    INDEX
    Explanations

    job sites

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unlocks
    0.66
     गिर
    0.65
    としている
    0.63
    ump
    0.63
     পুল
    0.62
    zm
    0.62
    Pooling
    0.61
     Sloven
    0.61
     తొలి
    0.60
    பே
    0.59
    POSITIVE LOGITS
     기대
    0.75
     componenti
    0.72
     flyers
    0.72
     opportunistic
    0.69
    菈
    0.69
     거
    0.69
     будущего
    0.69
     componente
    0.69
     flyer
    0.68
    cept
    0.66
    Act Density 0.001%

    No Known Activations