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

    Neuronpedia

    INDEX
    Explanations

    jump and transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barat
    1.01
     diri
    0.95
     zich
    0.91
     bert
    0.89
    𝑚
    0.88
    ことになる
    0.88
    时候
    0.87
    شوند
    0.86
    വധി
    0.85
    amiento
    0.85
    POSITIVE LOGITS
     jumping
    1.30
     Jump
    1.24
    跃
    1.23
     leaps
    1.20
     jump
    1.20
    Jump
    1.19
    scotch
    1.17
    jumping
    1.16
    jump
    1.15
    obstacles
    1.14
    Act Density 0.050%

    No Known Activations