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

    Neuronpedia

    INDEX
    Explanations

    ively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     want
    -0.07
     melting
    -0.06
     username
    -0.06
    �
    -0.06
    ح
    -0.06
    ็
    -0.06
    :not
    -0.06
     realise
    -0.06
     salt
    -0.06
     قرن
    -0.06
    POSITIVE LOGITS
     Liberties
    0.06
    emoc
    0.06
    ewise
    0.06
     Benedict
    0.06
     भर
    0.06
     nær
    0.06
    (px
    0.06
     빨
    0.06
    \OptionsResolver
    0.06
    428
    0.06
    Act Density 0.001%

    No Known Activations