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

    Neuronpedia

    INDEX
    Explanations

    detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endlessly
    -0.07
     Another
    -0.07
    عت
    -0.07
     الخار
    -0.07
    ונ
    -0.06
    uncture
    -0.06
    ינ
    -0.06
    _bit
    -0.06
     jane
    -0.06
    Txt
    -0.06
    POSITIVE LOGITS
     cohorts
    0.08
    TOKEN
    0.07
     mission
    0.07
    misión
    0.07
    abra
    0.07
     meticulous
    0.07
    _ES
    0.07
    _kelas
    0.07
     завис
    0.07
    锚
    0.06
    Act Density 0.015%

    No Known Activations