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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servent
    -0.08
    174
    -0.08
    jnë
    -0.08
     तत्व
    -0.08
    iciro
    -0.08
    -picked
    -0.08
     unfore
    -0.07
    fni
    -0.07
    eled
    -0.07
    NIC
    -0.07
    POSITIVE LOGITS
    جام
    0.07
    ulle
    0.07
    ulu
    0.07
     proportional
    0.07
    atures
    0.06
    ;
    0.06
    ${
    0.06
     بر
    0.06
    .Param
    0.06
    ules
    0.06
    Act Density 0.080%

    No Known Activations