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

    Neuronpedia

    INDEX
    Explanations

    Expressing feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grains
    -0.06
    ruption
    -0.06
    ικοί
    -0.06
    linger
    -0.06
    (todo
    -0.06
     voluntary
    -0.06
    ARATION
    -0.06
    くん
    -0.06
    کان
    -0.06
    počet
    -0.06
    POSITIVE LOGITS
    áž
    0.07
    عر
    0.07
     enjoyable
    0.06
    chyb
    0.06
    ัญญ
    0.06
     SPEED
    0.06
     FormsModule
    0.06
     relatively
    0.06
     myš
    0.06
     disg
    0.06
    Act Density 0.040%

    No Known Activations