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

    Neuronpedia

    INDEX
    Explanations

    Key details or descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ermeister
    0.43
    你去
    0.42
    狍
    0.38
    Timothy
    0.38
     Timothy
    0.38
     conspiring
    0.37
     वैलेंट
    0.37
     unmittel
    0.37
     maestro
    0.36
     creme
    0.36
    POSITIVE LOGITS
    :
    0.68
    ：
    0.53
    ↵
    0.50
    :\
    0.44
    у
    0.44
    Redirect
    0.43
    levant
    0.43
    K
    0.43
    :,
    0.43
    DO
    0.42
    Act Density 0.000%

    No Known Activations