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

    Neuronpedia

    INDEX
    Explanations

    Dates in career timelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faults
    -0.07
    _MAN
    -0.07
    (Command
    -0.07
    CreatedAt
    -0.06
    olecule
    -0.06
    рук
    -0.06
     deserving
    -0.06
     LOC
    -0.06
     Icons
    -0.06
    onestly
    -0.06
    POSITIVE LOGITS
     bitter
    0.07
     avait
    0.06
    地下
    0.06
     einen
    0.06
     borrowers
    0.06
     за
    0.06
    病
    0.06
    anchor
    0.06
     сьогодні
    0.06
    öh
    0.06
    Act Density 0.032%

    No Known Activations