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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    refs
    -0.07
    ually
    -0.07
    디오
    -0.07
    RAR
    -0.06
    ега
    -0.06
    akening
    -0.06
    Dim
    -0.06
    icamente
    -0.06
    ریان
    -0.06
     dere
    -0.06
    POSITIVE LOGITS
    .axes
    0.06
     ί
    0.06
     banc
    0.06
     Minuten
    0.06
     genera
    0.06
     zru
    0.06
     Тур
    0.06
    /project
    0.05
     Marco
    0.05
    gebung
    0.05
    Act Density 0.068%

    No Known Activations