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

    Neuronpedia

    INDEX
    Explanations

    laugh and smile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Viewer
    -0.08
    ogenous
    -0.08
     kapsam
    -0.08
    endo
    -0.07
     nhằm
    -0.07
    andal
    -0.07
     محس
    -0.07
    Generally
    -0.07
     בתחום
    -0.07
     kapsamında
    -0.07
    POSITIVE LOGITS
     damals
    0.13
     remembering
    0.12
     remembers
    0.11
     lembro
    0.11
     remembered
    0.11
     기억
    0.11
     recuerdo
    0.11
    曾
    0.11
    했던
    0.11
     erinnern
    0.11
    Act Density 0.044%

    No Known Activations