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

    Neuronpedia

    INDEX
    Explanations

    Unlikely/unattainable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ammonia
    -0.07
    転
    -0.06
    ำ
    -0.06
     fac
    -0.06
     чор
    -0.06
     withStyles
    -0.06
    尾
    -0.06
    แผ
    -0.06
    .Password
    -0.06
    strstr
    -0.06
    POSITIVE LOGITS
     aggression
    0.07
    Strike
    0.07
     insurg
    0.06
    봉
    0.06
     asks
    0.06
    ORED
    0.06
     Bermuda
    0.06
     enumerator
    0.06
     Jama
    0.06
     immune
    0.06
    Act Density 0.083%

    No Known Activations