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

    Neuronpedia

    INDEX
    Explanations

    consequence or comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poden
    0.42
    好
    0.39
    frist
    0.38
     boyunca
    0.37
    胭
    0.37
     получает
    0.36
     Telling
    0.36
     Relation
    0.36
    వా
    0.35
     Diseases
    0.35
    POSITIVE LOGITS
    /
    0.40
    rews
    0.38
    aid
    0.38
    antikan
    0.38
    ardu
    0.37
    นู
    0.37
    щь
    0.37
     (.
    0.37
    esas
    0.37
    Harvey
    0.37
    Act Density 0.000%

    No Known Activations