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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wool
    -0.07
    mented
    -0.07
     dejar
    -0.07
     serotonin
    -0.06
    .workflow
    -0.06
    ايش
    -0.06
     lake
    -0.06
     cheese
    -0.06
    CSR
    -0.06
    @interface
    -0.06
    POSITIVE LOGITS
     Reg
    0.07
    zeug
    0.06
    œ
    0.06
     To
    0.06
    REV
    0.06
     і
    0.06
    _LOOK
    0.06
    Utils
    0.06
    Persistence
    0.06
    ngör
    0.06
    Act Density 0.157%

    No Known Activations