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

    Neuronpedia

    INDEX
    Explanations

    Blaming something on someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulation
    -0.07
     parody
    -0.06
     channel
    -0.06
     manipulated
    -0.06
     landfill
    -0.06
     portrays
    -0.06
    Allen
    -0.06
    *.
    -0.06
    _placement
    -0.06
    vec
    -0.06
    POSITIVE LOGITS
     keyboardType
    0.07
     gc
    0.07
     Kyoto
    0.06
    (Bundle
    0.06
    (assigns
    0.06
    _PUS
    0.06
     lng
    0.06
    misc
    0.06
     गई
    0.06
     lawy
    0.06
    Act Density 0.010%

    No Known Activations