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

    Neuronpedia

    INDEX
    Explanations

    parentheses and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Levin
    -0.08
    Ctl
    -0.08
    'on
    -0.08
     rr
    -0.08
     atteint
    -0.07
     पूरी
    -0.07
     Lisp
    -0.07
    tijd
    -0.07
    _resume
    -0.07
    _LITERAL
    -0.07
    POSITIVE LOGITS
     Categoria
    0.08
    เสนอ
    0.08
    ങ്ങളിലും
    0.07
     coal
    0.07
     grain
    0.07
     bilateral
    0.07
     astfel
    0.07
    .combo
    0.07
    ારમાં
    0.07
    andas
    0.07
    Act Density 0.001%

    No Known Activations