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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sincerity
    -0.07
     MCP
    -0.07
     березня
    -0.06
     thigh
    -0.06
    ram
    -0.06
    _phr
    -0.06
     Mighty
    -0.06
     Mark
    -0.06
    เกล
    -0.06
     各
    -0.06
    POSITIVE LOGITS
    ################################################################
    0.07
     comet
    0.07
    .');
↵
    0.06
     )
↵
    0.06
    icate
    0.06
    ائل
    0.06
    )↵
    0.06
     dept
    0.06
    ้อย
    0.06
    áh
    0.06
    Act Density 0.001%

    No Known Activations