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

    Neuronpedia

    INDEX
    Explanations

    programming/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    think
    -0.06
     "__
    -0.06
     clans
    -0.06
     Cricket
    -0.06
     sword
    -0.06
    ican
    -0.06
     Frequ
    -0.06
     hazard
    -0.05
    need
    -0.05
    .ab
    -0.05
    POSITIVE LOGITS
     지난
    0.08
    _WARNINGS
    0.07
     mô
    0.06
     prem
    0.06
     zprávy
    0.06
    خل
    0.06
     rewritten
    0.06
     ткани
    0.06
    ا
    0.06
     Luke
    0.06
    Act Density 0.000%

    No Known Activations