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

    Neuronpedia

    INDEX
    Explanations

    saving/stopping

    np_max-act · gemini-2.0-flash

    The neuron is looking for descriptions of goalkeeping actions, especially mentions of saves or denials.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     로
    -0.07
     SharedModule
    -0.07
    いた
    -0.07
     السكان
    -0.06
    合作
    -0.06
    decorators
    -0.06
     ciphertext
    -0.06
     tonight
    -0.06
    -called
    -0.06
     Conversely
    -0.06
    POSITIVE LOGITS
    IMARY
    0.07
     mining
    0.06
    ья
    0.06
     opatření
    0.06
     Ore
    0.06
    Sig
    0.06
    grading
    0.06
    Opens
    0.06
    ��
    0.06
    ập
    0.06
    Act Density 0.006%

    No Known Activations