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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     malleable
    0.34
     ruthless
    0.32
     inspect
    0.32
     formalized
    0.32
     formal
    0.32
     mim
    0.32
     attentive
    0.31
     granular
    0.31
     astrophys
    0.30
     immisc
    0.30
    POSITIVE LOGITS
    agascar
    0.42
    जीलैंड
    0.42
     **,
    0.40
     ウ
    0.40
    ͯ
    0.40
     եւ
    0.40
    ៧
    0.38
    ik
    0.38
    spapers
    0.38
    ications
    0.38
    Act Density 0.000%

    No Known Activations