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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itude
    -0.07
     EV
    -0.07
     stal
    -0.07
    _UPLOAD
    -0.07
    Requested
    -0.07
     plum
    -0.06
    idenav
    -0.06
     RNG
    -0.06
     murderous
    -0.06
     sat
    -0.06
    POSITIVE LOGITS
    options
    0.07
    \Seeder
    0.07
    )))
    0.07
    _crossentropy
    0.07
     Adoption
    0.06
     Bone
    0.06
     deser
    0.06
    _reservation
    0.06
    ))?
    0.06
    registration
    0.06
    Act Density 0.000%

    No Known Activations