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

    Neuronpedia

    INDEX
    Explanations

    target and programming methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verh
    0.46
    ertain
    0.41
     obstruct
    0.39
    🐮
    0.39
     prescribes
    0.38
     Determines
    0.38
     supplement
    0.37
     rayon
    0.37
     وش
    0.37
     Easily
    0.37
    POSITIVE LOGITS
    getTargetContext
    0.73
    targetContext
    0.70
    target
    0.57
    targets
    0.56
    Target
    0.56
     target
    0.55
    TARGET
    0.55
    Targets
    0.54
    ターゲット
    0.53
     Target
    0.51
    Act Density 0.000%

    No Known Activations