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

    Neuronpedia

    INDEX
    Explanations

    poison ivy, modulate, Asian countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equalization
    0.51
     hating
    0.45
     mating
    0.44
     archived
    0.44
    UIActions
    0.44
     inspiring
    0.43
     தி
    0.43
     alarming
    0.43
     KMS
    0.43
     equalize
    0.43
    POSITIVE LOGITS
    рович
    0.51
    ш
    0.51
    ра
    0.49
    𝙘
    0.49
    Nombre
    0.48
    р
    0.47
     nombre
    0.47
    ка
    0.47
    zione
    0.47
    ческа
    0.47
    Act Density 0.000%

    No Known Activations