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

    Neuronpedia

    INDEX
    Explanations

    resources for psychology and health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horno
    0.99
     rhombus
    0.98
    𒇻
    0.97
     sencillo
    0.95
    𒌨
    0.95
    incia
    0.94
    𒌌
    0.93
    罒
    0.93
     spacerItem
    0.93
     vacuna
    0.93
    POSITIVE LOGITS
    0.87
    K
    0.80
     R
    0.79
     K
    0.77
    N
    0.77
     O
    0.77
    ab
    0.76
     F
    0.75
     Living
    0.73
     M
    0.73
    Act Density 0.102%

    No Known Activations