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

    Neuronpedia

    INDEX
    Explanations

    emotional states and individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     precio
    0.48
     munic
    0.41
     गह
    0.40
    exists
    0.40
    salad
    0.40
    শ্রেণীর
    0.40
     mejorar
    0.39
    trag
    0.39
     ll
    0.39
     Tin
    0.39
    POSITIVE LOGITS
     lifting
    0.41
     lifts
    0.36
    elerde
    0.36
    HLER
    0.36
    BLIC
    0.36
    ני
    0.35
     strains
    0.35
     Lift
    0.35
    τρέ
    0.35
     Lifting
    0.35
    Act Density 0.001%

    No Known Activations