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

    Neuronpedia

    INDEX
    Explanations

    references or citations to prior works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with Re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    angdong
    -0.61
    citos
    -0.58
    cplusplus
    -0.58
    ciun
    -0.56
    akaian
    -0.56
    nson
    -0.56
    idopsis
    -0.54
    ctically
    -0.54
    __*/
    -0.54
    cular
    -0.54
    POSITIVE LOGITS
     Re
    1.96
    Re
    1.86
     re
    1.07
     RE
    0.99
     Ре
    0.84
     Rew
    0.73
    Ре
    0.72
     Reggie
    0.68
     Reh
    0.66
     Se
    0.66
    Act Density 0.010%

    No Known Activations