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

    Neuronpedia

    INDEX
    Explanations

    build a story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szpital
    1.36
     तकनीक
    1.36
     experto
    1.24
    ୯
    1.22
    𝘬
    1.21
    𝘺
    1.18
    ość
    1.18
    SIGNAL
    1.17
     인해
    1.15
     workable
    1.15
    POSITIVE LOGITS
    ج
    1.19
    ing
    1.11
    s
    1.10
    vä
    1.06
    1.01
    u
    1.01
    DSS
    1.00
    ied
    1.00
    าตุ
    0.96
    h
    0.95
    Act Density 0.001%

    No Known Activations