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

    Neuronpedia

    INDEX
    Explanations

    shared technical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jacent
    -0.94
     melhores
    -0.90
     celebridades
    -0.90
    や
    -0.88
    Serious
    -0.86
     quintessential
    -0.86
    lda
    -0.85
     echar
    -0.82
     intenta
    -0.82
    vener
    -0.82
    POSITIVE LOGITS
     between
    1.31
     resources
    1.03
     amongst
    1.02
     بين
    1.02
    among
    1.00
     with
    1.00
     Antara
    0.96
     pei
    0.95
     responsibility
    0.92
    between
    0.91
    Act Density 0.017%

    No Known Activations