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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erotic
    -0.07
    coming
    -0.07
     Bust
    -0.07
    弱
    -0.07
     э
    -0.07
     bust
    -0.06
     mojo
    -0.06
    oor
    -0.06
    Hook
    -0.06
     toned
    -0.06
    POSITIVE LOGITS
    ульт
    0.06
    :"<<
    0.06
     assigns
    0.06
    .abort
    0.06
    _USERNAME
    0.06
     wrongdoing
    0.06
    ๊
    0.06
     Logout
    0.06
    Throws
    0.06
    Karen
    0.06
    Act Density 0.000%

    No Known Activations