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

    Neuronpedia

    INDEX
    Explanations

    Visual representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     top
    -0.07
     task
    -0.07
    Mech
    -0.06
     constructive
    -0.06
     fab
    -0.06
    (score
    -0.06
     Plant
    -0.06
    यर
    -0.06
     wrote
    -0.06
     Tut
    -0.06
    POSITIVE LOGITS
    "]:
    0.06
     �
    0.06
    :".$
    0.06
    ですね
    0.06
     дити
    0.06
    0.06
     ApiController
    0.06
    annel
    0.06
    ــــ
    0.06
    )",
    0.06
    Act Density 0.018%

    No Known Activations