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

    Neuronpedia

    INDEX
    Explanations

    arm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lookout
    -0.07
    dera
    -0.07
    _LABEL
    -0.06
    itical
    -0.06
    Timeout
    -0.06
    gnore
    -0.06
     directives
    -0.06
     disobed
    -0.06
     дня
    -0.06
     longest
    -0.06
    POSITIVE LOGITS
     approaching
    0.07
     Lal
    0.07
     dul
    0.07
     fail
    0.07
     mars
    0.07
     Af
    0.06
     Ram
    0.06
     XC
    0.06
     σει
    0.06
     La
    0.06
    Act Density 0.003%

    No Known Activations