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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suicide
    -0.07
    -shift
    -0.07
    SqlCommand
    -0.07
    CTest
    -0.06
    -click
    -0.06
    -ion
    -0.06
    _CHIP
    -0.06
    Helpers
    -0.06
    .espresso
    -0.06
     PASS
    -0.06
    POSITIVE LOGITS
    uggestions
    0.07
     ー
    0.06
     za
    0.06
     Gret
    0.06
    oop
    0.06
    (secret
    0.06
    —he
    0.06
    هه
    0.05
     seventeen
    0.05
     remind
    0.05
    Act Density 0.005%

    No Known Activations