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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SAVE
    -0.06
    .Sn
    -0.06
     тв
    -0.06
    ΑΔ
    -0.06
    OUN
    -0.06
     Issues
    -0.06
     agenda
    -0.06
     ""↵↵
    -0.06
     fields
    -0.06
     row
    -0.06
    POSITIVE LOGITS
    182
    0.07
    acerb
    0.07
     움직
    0.07
     břez
    0.07
    buah
    0.07
    cred
    0.06
     cohesive
    0.06
    ush
    0.06
    크
    0.06
    177
    0.06
    Act Density 0.002%

    No Known Activations