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

    Neuronpedia

    INDEX
    Explanations

    contact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TEXTURE
    -0.06
     hill
    -0.06
     coffin
    -0.06
    orghini
    -0.06
     又
    -0.06
     بشر
    -0.06
     Levi
    -0.06
     세
    -0.06
     вір
    -0.06
    وش
    -0.06
    POSITIVE LOGITS
    >Contact
    0.08
    فاق
    0.07
    conditional
    0.07
    genome
    0.06
     Sy
    0.06
    ційно
    0.06
    ?↵↵
    0.06
     numbered
    0.06
    Elect
    0.06
    MOD
    0.06
    Act Density 0.012%

    No Known Activations