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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'altra
    -0.08
    _DO
    -0.08
    (ix
    -0.08
    _EXPR
    -0.07
     வா�
    -0.07
    -ground
    -0.07
     Aph
    -0.07
     obligatorio
    -0.07
     aspirin
    -0.07
    University
    -0.07
    POSITIVE LOGITS
     disruptions
    0.09
     trusty
    0.08
     FStar
    0.07
     വ്യ
    0.07
     (
    0.07
     gestão
    0.07
    /or
    0.07
    /ou
    0.07
     disruptive
    0.07
     nette
    0.07
    Act Density 0.122%

    No Known Activations