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

    Neuronpedia

    INDEX
    Explanations

    team vs team matches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contrast
    0.42
     traction
    0.40
     contraste
    0.38
     coincided
    0.38
     Contrast
    0.37
    間に
    0.37
     touch
    0.37
     en
    0.37
     wood
    0.36
     mara
    0.36
    POSITIVE LOGITS
     vs
    0.66
     बनाम
    0.65
     Vs
    0.59
    🆚
    0.54
    vs
    0.54
     versus
    0.47
     Versus
    0.45
     dvara
    0.44
     विराजमान
    0.44
    Vs
    0.42
    Act Density 0.007%

    No Known Activations