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

    Neuronpedia

    INDEX
    Explanations

    entering or reaching places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DeSantis
    0.54
     patriots
    0.50
     berikut
    0.49
     affidavit
    0.47
     numberWith
    0.47
    s
    0.47
     Astronom
    0.47
     Affidavit
    0.46
     Councilor
    0.46
    ms
    0.46
    POSITIVE LOGITS
     wonderland
    0.58
     границы
    0.56
     realm
    0.53
     turmoil
    0.52
    ંજ
    0.52
     aquilo
    0.51
     Такая
    0.49
     reach
    0.48
     the
    0.48
     realms
    0.48
    Act Density 0.015%

    No Known Activations