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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ames
    -0.07
    delivr
    -0.07
    chter
    -0.07
    ctxt
    -0.06
    \System
    -0.06
    iris
    -0.06
    seven
    -0.06
     увелич
    -0.06
    ْه
    -0.06
    pires
    -0.06
    POSITIVE LOGITS
     Gef
    0.07
     signals
    0.07
     Essential
    0.07
    ást
    0.07
     brake
    0.06
     Ry
    0.06
    男
    0.06
     Much
    0.06
     Entities
    0.06
     antibody
    0.06
    Act Density 0.001%

    No Known Activations