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

    Neuronpedia

    INDEX
    Explanations

    image color space and layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rober
    0.41
     നിങ്ങൾ
    0.41
    ཋ
    0.40
    Š
    0.40
    Joshua
    0.38
    ählte
    0.37
    성과
    0.37
     গৃহে
    0.37
    에서의
    0.36
    และการ
    0.36
    POSITIVE LOGITS
     (
    0.45
     SCP
    0.41
     (&
    0.38
     crushing
    0.38
     imit
    0.38
    ⊃
    0.37
     (!
    0.37
     (/
    0.37
     dominating
    0.37
    ංග
    0.37
    Act Density 0.018%

    No Known Activations