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

    Neuronpedia

    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rifles
    -0.07
    -alert
    -0.06
    نامج
    -0.06
    finally
    -0.06
    cala
    -0.06
    emporary
    -0.05
    다가
    -0.05
    nějších
    -0.05
     autonom
    -0.05
    difficulty
    -0.05
    POSITIVE LOGITS
     sanitation
    0.07
     defeats
    0.07
     여기
    0.07
     beneficial
    0.07
    _job
    0.07
     справи
    0.07
    оци
    0.07
    .insert
    0.06
     molest
    0.06
    ="")↵
    0.06
    Act Density 0.002%

    No Known Activations