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

    Neuronpedia

    INDEX
    Explanations

    food and drink appetizers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.85
    E
    0.84
    O
    0.82
    P
    0.82
    U
    0.76
    A
    0.75
    S
    0.72
    R
    0.69
    TR
    0.68
    I
    0.68
    POSITIVE LOGITS
     idée
    0.53
     идеи
    0.53
     причине
    0.52
     остров
    0.51
     офис
    0.51
    يل
    0.50
     bombs
    0.50
     худож
    0.49
     потребности
    0.49
    者的
    0.49
    Act Density 0.060%

    No Known Activations