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

    Neuronpedia

    INDEX
    Explanations

    to + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    炘
    0.53
    Dealing
    0.49
    Repeating
    0.49
     అంశ
    0.48
    वैसे
    0.48
    Obviously
    0.47
    сло
    0.46
    담당
    0.46
    יל
    0.46
    แน่นอน
    0.46
    POSITIVE LOGITS
    }{\
    0.52
     that
    0.47
     V
    0.47
    style
    0.47
     T
    0.46
     setup
    0.46
     N
    0.45
     O
    0.45
     Enfer
    0.45
     X
    0.44
    Act Density 0.004%

    No Known Activations