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

    Neuronpedia

    INDEX
    Explanations

    phases of a plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.38
    9
    1.34
    1
    1.27
    7
    1.24
    8
    1.21
    5
    1.19
    4
    1.14
    3
    1.12
    6
    1.10
    0
    1.08
    POSITIVE LOGITS
     multifaceted
    1.12
    <unused2148>
    1.11
     leveraging
    1.08
    <unused1121>
    1.07
    <unused2175>
    1.07
     societal
    1.07
     pretensions
    1.07
     prevalent
    1.06
     socio
    1.04
     harnessing
    1.04
    Act Density 0.060%

    No Known Activations