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

    Neuronpedia

    INDEX
    Explanations

    under development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lean
    0.37
     LMP
    0.36
    mach
    0.36
    strain
    0.36
    Ry
    0.36
     Lean
    0.36
    dash
    0.35
     Strain
    0.35
    call
    0.35
     Vi
    0.35
    POSITIVE LOGITS
    MJ
    0.37
    ゴン
    0.37
    ष्णा
    0.36
     plomb
    0.35
     plunger
    0.35
     piede
    0.35
     fis
    0.34
     Thess
    0.34
     Bumble
    0.34
    Bj
    0.34
    Act Density 0.006%

    No Known Activations