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

    Neuronpedia

    INDEX
    Explanations

    Australia, Best, Short, Summer, Immune, Pang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estaría
    0.43
     honom
    0.42
     całej
    0.42
     wszyscy
    0.41
     samano
    0.41
    мии
    0.41
     bestow
    0.41
     principalTable
    0.41
    .”—
    0.40
     aquello
    0.40
    POSITIVE LOGITS
    G
    0.57
    A
    0.56
     A
    0.55
    H
    0.54
     R
    0.52
    Ar
    0.52
     The
    0.52
     Ar
    0.51
     J
    0.50
    J
    0.50
    Act Density 0.001%

    No Known Activations