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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    andan
    -0.07
    衾
    -0.07
          ↵↵
    -0.07
     desarrollo
    -0.07
    ์
    -0.07
    營
    -0.07
    ardo
    -0.07
     alunos
    -0.07
     presente
    -0.07
    s
    -0.07
    POSITIVE LOGITS
    -cr
    0.07
    友善
    0.07
    /cop
    0.07
    isor
    0.07
    /jav
    0.07
     Cmd
    0.06
    mètre
    0.06
     Delegate
    0.06
    .fac
    0.06
     Generally
    0.06
    Act Density 0.030%

    No Known Activations