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

    Neuronpedia

    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hug
    -0.08
     GEO
    -0.07
     heal
    -0.07
     CO
    -0.07
    OTT
    -0.07
     ethanol
    -0.07
     UPC
    -0.07
    ole
    -0.07
     KO
    -0.06
    ційної
    -0.06
    POSITIVE LOGITS
     상대
    0.07
    .↵↵↵↵↵↵↵↵
    0.07
    ClassNotFoundException
    0.06
    átor
    0.06
    (details
    0.06
    슴
    0.06
    .leading
    0.06
    appro
    0.06
    �
    0.06
    .getDeclared
    0.06
    Act Density 0.008%

    No Known Activations