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

    Neuronpedia

    INDEX
    Explanations

    case sensitivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `=`,
    0.56
    pInBuffer
    0.55
     pojem
    0.55
    édié
    0.55
     “‘
    0.54
    thoughtId
    0.54
     toolPath
    0.53
     previewBuilder
    0.52
    滸
    0.52
     перспекти
    0.52
    POSITIVE LOGITS
    mon
    0.54
    V
    0.52
    she
    0.51
    man
    0.50
    She
    0.50
    Mon
    0.49
    G
    0.49
    Doll
    0.49
    men
    0.48
    than
    0.48
    Act Density 0.000%

    No Known Activations