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

    Neuronpedia

    INDEX
    Explanations

    between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alignParentRight
    0.37
    栦
    0.37
     Importing
    0.36
    entum
    0.35
    籠
    0.35
     Inicial
    0.35
     lapin
    0.34
    semble
    0.34
     ಕಟ್ಟ
    0.34
    眷
    0.34
    POSITIVE LOGITS
     intervening
    2.47
     Zwischen
    2.20
     between
    2.19
    中间
    2.19
     중간
    2.19
    Between
    2.17
     interposed
    2.17
     Between
    2.16
     промежу
    2.16
    中間
    2.11
    Act Density 0.067%

    No Known Activations