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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    0.80
    2
    0.77
    는
    0.77
    F
    0.74
    р
    0.74
    ite
    0.73
    ant
    0.71
    0
    0.71
     or
    0.70
    ρ
    0.68
    POSITIVE LOGITS
     évaluation
    0.88
    kannya
    0.88
     établ
    0.82
     épars
    0.82
     effic
    0.81
     antérieurs
    0.81
     interno
    0.80
     osserv
    0.80
     abhiv
    0.80
     déta
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.