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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hook
    -0.08
     hooking
    -0.07
     superior
    -0.07
     Selector
    -0.07
    ielle
    -0.07
     vencer
    -0.07
    stdbool
    -0.07
     slimming
    -0.07
    oddi
    -0.07
    otive
    -0.07
    POSITIVE LOGITS
    双方
    0.14
     gegense
    0.10
     birbir
    0.10
     intercambio
    0.10
     berlangsung
    0.09
     બંને
    0.09
     échanges
    0.09
     échange
    0.09
     ಇಬ್ಬ
    0.09
    _busy
    0.09
    Act Density 0.020%

    No Known Activations