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

    Neuronpedia

    INDEX
    Explanations

    past actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Об
    -0.07
     puts
    -0.07
     stole
    -0.07
    .levels
    -0.07
    allenges
    -0.07
    069
    -0.07
    문을
    -0.07
     �
    -0.06
     replacing
    -0.06
     pistols
    -0.06
    POSITIVE LOGITS
    ीवन
    0.06
    、《
    0.06
     teď
    0.06
    _seg
    0.06
    =o
    0.06
     Antony
    0.06
     Disabilities
    0.06
     života
    0.06
     Zucker
    0.06
    "net
    0.06
    Act Density 0.065%

    No Known Activations