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

    Neuronpedia

    INDEX
    Explanations

    plan / plans / planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beasts
    0.52
     treks
    0.51
     or
    0.49
    iggers
    0.49
     voyages
    0.48
    tdown
    0.48
     expeditions
    0.48
     treasures
    0.47
    b
    0.47
    bikes
    0.47
    POSITIVE LOGITS
     FIF
    0.51
     refracting
    0.50
     príncipe
    0.46
    Cuenta
    0.45
     ISP
    0.45
    0.45
     BET
    0.45
    是一种
    0.45
    适用于
    0.45
     teljes
    0.44
    Act Density 0.000%

    No Known Activations