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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kterého
    -0.07
    _module
    -0.07
    xima
    -0.06
     organis
    -0.06
    нив
    -0.06
     sido
    -0.06
     longitud
    -0.06
     Sco
    -0.06
    _CheckedChanged
    -0.06
    <h
    -0.06
    POSITIVE LOGITS
     hit
    0.07
     inside
    0.07
     delivers
    0.07
     able
    0.06
     mother
    0.06
     damn
    0.06
     hooked
    0.06
     envy
    0.06
     unsettling
    0.06
    ACING
    0.06
    Act Density 0.008%

    No Known Activations