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

    Neuronpedia

    INDEX
    Explanations

    essential technical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letteratura
    0.45
    гів
    0.42
    媤
    0.41
     successivement
    0.40
     respectivement
    0.40
    রাগ
    0.39
    눅
    0.39
     présentes
    0.38
     eine
    0.38
     précis
    0.38
    POSITIVE LOGITS
     confronts
    0.42
    Branch
    0.37
     maxLength
    0.36
    හර
    0.36
    伸
    0.36
     mysterious
    0.35
    Protein
    0.35
    決
    0.35
     სახელმწიფ
    0.35
     powerfully
    0.35
    Act Density 0.000%

    No Known Activations