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

    Neuronpedia

    INDEX
    Explanations

    physical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Running
    0.38
    Park
    0.36
    았
    0.35
    тва
    0.34
    Because
    0.34
    Sch
    0.33
    You
    0.33
    Contra
    0.33
    잤
    0.32
    Bundle
    0.32
    POSITIVE LOGITS
     counterparts
    0.42
     versions
    0.40
     equivalents
    0.40
     hallmarks
    0.38
     analogs
    0.38
     mechanisms
    0.37
     முறையில்
    0.37
     versões
    0.36
     models
    0.35
     methods
    0.35
    Act Density 0.160%

    No Known Activations