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

    Neuronpedia

    INDEX
    Explanations

    food reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ˘
    -0.07
    igeria
    -0.07
     информации
    -0.07
    Broadcast
    -0.06
    accountId
    -0.06
     Numbers
    -0.06
     opponents
    -0.06
    _ctl
    -0.06
    _occ
    -0.06
    -fetch
    -0.06
    POSITIVE LOGITS
     laisse
    0.07
    defines
    0.06
    ;margin
    0.06
    　イ
    0.06
     ganz
    0.06
     reinforcement
    0.06
     '-';↵
    0.06
     Zig
    0.05
     ""},↵
    0.05
    (sym
    0.05
    Act Density 0.021%

    No Known Activations