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

    Neuronpedia

    INDEX
    Explanations

    command, cd, rm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പിന്തുണ
    0.39
     playmaker
    0.36
     blogger
    0.36
     tenure
    0.36
    യിലും
    0.34
     trailbl
    0.34
     vời
    0.34
     scheme
    0.33
     Workforce
    0.33
     finance
    0.33
    POSITIVE LOGITS
     which
    0.47
    iccation
    0.44
    ütfen
    0.43
    ymptoms
    0.43
    which
    0.42
     beings
    0.42
    nommen
    0.42
    lowing
    0.41
     enfermedades
    0.41
    %.
    0.41
    Act Density 0.001%

    No Known Activations